© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58249
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and software generation headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hướng
    -0.89
     okolo
    -0.86
     werfen
    -0.84
     duża
    -0.84
    caucasian
    -0.84
    comfor
    -0.83
    ników
    -0.83
    kovo
    -0.83
    ILabel
    -0.81
    」、
    -0.81
    POSITIVE LOGITS
    =
    1.26
     =
    0.88
     trus
    0.85
    true
    0.83
     Dod
    0.82
    bietern
    0.81
    否
    0.80
    IDI
    0.79
    ~=
    0.78
    极限
    0.78
    Activations Density 0.000%

    No Known Activations